segformer_400samples_13of20epochs_4batch

This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.1547
• Validation Loss: 0.2291
• Epoch: 12

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 6e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
0.4764	0.2749	0
0.3092	0.3437	1
0.2745	0.3007	2
0.2509	0.2527	3
0.2402	0.2469	4
0.2357	0.1991	5
0.2091	0.1949	6
0.2095	0.1833	7
0.1968	0.1662	8
0.1612	0.1446	9
0.1680	0.1658	10
0.1486	0.2235	11
0.1547	0.2291	12

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Tokenizers 0.15.2